Guan Wang

reinforcement learning (2) temporal modeling (2) scene graph generation (2) offline reinforcement learning (1) graph laplacian (1) neuromorphic computing (1) knowledge transfer (1) object detection (1) human feedback (1) weakly supervised learning (1) temporal reasoning (1) cross-modal learning (1) policy learning (1) video understanding (1) model adaptation (1) graph clustering (1) spectral analysis (1) bilevel optimization (1) interactive learning (1) model compression (1)